Active Vision in Robotics for Optimal Mobile Camera Sensor Planning

Active vision or perception is one that can manipulate the viewpoint of the cameras in order to investigate the environment, and get better information from it. It mostly encourages the idea of moving a visual sensor to constrain interpretation of its environment. This research in active vision is concerned with determining the 3D pose and configuration for visual sensor, it plays an important role in by purposefully configuring and placing the visual sensor at several positions to observe a target, obtain the optimal quality of data as the input of objection detection and pose estimation technologies.

Faculty Supervisor:

Florian Shkruti

Student:

Angran Li

Partner:

Epson Canada Ltd

Discipline:

Computer science

Sector:

Manufacturing

University:

University of Toronto